Plugins
Browse, filter, and install DeepSeek-Harness plugins.
177 plugins found
model-failover-manager
liaoyuqing/model-failover-manager
Model picker dialog with routing groups: a model that keeps failing hands the turn to the next usable model in its group, and the dialog also carries a metrics dashboard and a free-channel tab. That tab installs six channel plugins — Our Free Model (the only one that needs no login or API key), CodeArts, WorkBuddy, Trae, Qoder and Providers Hub — whose providers cover 23 platforms: Huawei Cloud CodeArts, Tencent CodeBuddy, WorkBuddy, Youdao LobsterAI, Qoder, TRAE, Cline, iFlytek Loomy, SenseTime Raccoon, MiniMax, Zhipu ZCode, Gemini Code Assist, Alibaba Accio, iFlytek AStudio, OpenCode, OfficeAce, AutoClaw, ModelScope, Qiniu, Codely, MonkeyCode, Baizhi Cloud and MagiCrew.
dsh-dual-checkin
g57651/dsh-dual-checkin
Checks in Trae and WorkBuddy daily from local login files, with a sidebar status and credits panel.
dsh-workbuddy-ppt
superstructurejh/dsh-workbuddy-ppt
Generates editable PPTX decks in DSH with a bundled authoring Skill, deterministic PPTD scene checks, native PowerPoint objects, and local PPTD source-project delivery.
dsh-hybrid-memory
frog755/dsh-hybrid-memory
Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.
dsh-skills-hub
lcthe/dsh-skills-hub
DSH Skill Manager: browse, enable/disable, import from Codex/Claude Code/ZCode/WorkBuddy/QCoderWork, auto-discover skills with symlink support.
new-project-init
warm-flame-core/new-project-init
Project documentation scaffolding skill: question-driven setup of project standards, AI-collaboration workflows, and memory discipline across DSH, Reasonix, Claude Code, and Codex.
dsh-plugin-thinking-api
qjf44/dsh-plugin-thinking-api
One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.
dsh-skillbox
fenshal/dsh-skillbox
One page for every skill on your machine: lists what DSH, WorkBuddy, Claude Code, Codex and Doubao have installed, imports any of them as a DSH skill, and discovers more on GitHub or the ClawHub directory (sorted by real downloads). Experts can be attached per session with a per-turn avatar header.
dsh-local-trim
leonlee114514/dsh-local-trim
One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.
dsh-grok-buddy
devzer0o0/dsh-grok-buddy
Puts Grok Bot's own face in the DSH sidebar session list: each row's status dot becomes a living GrokBot avatar whose six motions read as idle, working, waiting, blocked, thinking and done — color marks the project, motion marks the state.
dsh-agent-llm
mnemosyneos/dsh-agent-llm
DeepSeek Harness 插件:把本机已登录的 WorkBuddy / WorkBuddy AI / Hermes Agent 大模型接入 DSH 模型库,显示与 Agent 一致的模型名称、积分倍率与免费额度。
dsh-plugins
zhiqiangme/dsh-plugins
DSH 启动时默认拉起 WorkBuddy2API Hub(127.0.0.1:7863),可切换 wb2api;幂等、静默、退出时只停自己拉起的进程。
dsh-memory
bangbang-03/dsh-memory
Long-term memory scoped to the DSH workspace. A session opens with a one-line-per-memory index - bodies are fetched on demand by the `memory` tool, so the same character budget holds about three times as many entries - and when a turn ends a purely local search over the last user message pulls the matching memories into the next briefing at no model cost. Optional auto-capture distils a stretch of conversation into structured memories; in draft mode they wait in an approval queue instead of landing directly. A portrait layer keeps a workspace and a global picture, rewritten from the journal and the records, with the same draft-or-direct choice. Settings → Memory holds the archive, list and timeline views, a health check (duplicate clusters, stale entries, broken links), the supersede version chain with rollback, and a read-only scan that imports existing WorkBuddy / Qoder memory files.
dsh-takeover
ikeasven69/dsh-takeover
Session takeover: read-only pull local sessions from nine external agents (Claude Code, Codex, OpenCode, ZCode, Pi, WorkBuddy, Cursor, Grok, Gemini CLI) into distilled six-section handoff cards — one click on the Relay chip takes over. /handoff checks the current session into the handoff: 1 open-protocol inbox (~/.handoff, consume-once with machine-signature tamper detection); any agent picks up on start and continues. Memory files ride with cards; cross-machine relay is one env var away.
dsh-connect-workbuddy
ethanweave/dsh-connect-workbuddy
Runs a local OpenAI-compatible gateway so DSH can use the model quota of a logged-in Tencent CodeBuddy (WorkBuddy) account: one-shot installer with SHA256 verification, logon scheduled task with duplicate-launch guard, manage.ps1 for status/start/stop/restart/logs/update/uninstall, and an agent skill that drives setup and troubleshooting.
dsh-agent-preset-recommender
leemancheung/dsh-agent-preset-recommender
Bounded, privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy metadata: atomically aggregates keyed evidence and deterministically advises built-in DSH presets and optional capabilities—without content retention, network access, or preset mutation.
dsh-plugin-buddy
pilothowe/dsh-plugin-buddy
No manual browsing or keyword guessing: describe a task in chat and Plugin Buddy searches the DSH community plugin catalog for you with multiple keyword groups, ranks matches by relevance and quality signals, and turns a matching plugin README and manifest into grounded onboarding steps. On a high-confidence match it asks before switching to a plugin.
dsh-credit-expiry
526365412/dsh-credit-expiry
Credit expiry panel for WorkBuddy, Trae, MiniMax Code, Qoder and Doubao: a sidebar row shows each credit pool balance and its nearest expiry date, and the full page adds expiry buckets, a filterable credit ledger, an expiry calendar with per-platform layers, 7/14/30-day spend charts, the sessions that spent credits, a per-platform subscription and quota overview, expiry notifications, and CSV/JSON export. Read routes accept any loopback caller without a token, so a page open in your browser can read the ledger; write routes (/keys and /notify) reject cross-origin requests. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-atc
littleyellowbicycle/dsh-atc
One sidebar panel listing every local coding agent's sessions (DSH, codex, opencode, WorkBuddy, Gemini, ZCode, MiniMax) with real titles and turn-based status, read from local stores only. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-imperial-court
shilaoban666/dsh-imperial-court
Implements DeepSeek Harness's super-agent (router–worker) design on your own machine: a resident router, the Chancellor's Office, splits a request into tasks, triages and queues them by fixed rules without model calls, and starts each one as an isolated worker on its own git worktree and branch, surfacing only what needs your decision; an unattended mode repairs failed audits and archives passed ones. Inside each task the coding CLIs run as a Tang-dynasty court: one tool drafts a plan, a second reviews or vetoes it, six ministries work in parallel by dependency, an inspector checks each output and a final audit runs before you approve, and nothing is merged until then. Supports Claude Code, Codex, Gemini CLI, Cursor CLI, OpenCode, Qwen Code, WorkBuddy and DSH itself via dsh headless, with a tool catalog that shows install commands, per-call token and cost accounting with budgets, and an English Roman Senate mode.
dsh-workbuddy-account-care
eeetechen/dsh-workbuddy-account-care
dsh-workbuddy 账号呵护:dsh-connect-workbuddy 的配套辅助插件。按 WorkBuddy 官方接口字段与安装包文件名解析出的版本号(取高者)与本地基线比对,不一致就提示并停用 dsh-connect-workbuddy、软结束正在用它的会话,并在界面顶部挂持久水印;同时自动升级 dsh-connect-workbuddy 自身。
dsh-provider-doctor
tangyixiao/dsh-provider-doctor
Read-only diagnosis for a model provider that stopped working. Walks the connection chain one link at a time — host runtime and profile identity, the plugin row, whether the provider route is registered, whether it is configurable, the credential metadata the provider itself reports, the model catalogue, the provider's own diagnostic and the last recorded request — and labels each link observed, inferred or unavailable rather than guessing. Diagnoses the `workbuddy`, `workbuddy-ai` and `zcode-cli` routes from their plugins' public diagnostic commands, and adds a sidebar panel plus a copyable redacted report. The offline pass sends no model request, starts no process and reads no credential file; the connection check is a separate opt-in the panel describes before running it. Version 0.1.10 applies the synchronous Host request policy followed by owner admission to all five HTTP routes before diagnostic actions; missing, throwing, malformed or asynchronous admission services fail closed. Declared hosts are DSH 0.2.2-rc.1 and 0.2.2-rc.3.
workbuddy-monitor
9963kk/workbuddy-monitor
Monitors WorkBuddy credit usage and the free-tier 24-hour window quota (local estimate) in real time, with composer badges, a settings panel, multi-account rotation and free/paid plan detection.
dsh-feishu-client
cube-ai/dsh-feishu-client
DSH Feishu Client. 1) Users (humans) access remote agents through the UI provided by this plugin; 2) The local DSH accesses remote agents by calling the tools provided by this plugin. Supported remote agents include but are not limited to DSH, OpenClaw, WorkBuddy, Weknora, etc.